On: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

[gpugreg]

    > those things are not deterministic

Determinism was an explicit goal of DeepSeek-V4. From their paper: https://arxiv.org/html/2606.19348v1#S3.SS3

    > we implement end-to-end, bitwise batch-invariant, and deterministic kernels with minimal performance overhead

Of course, providers may not implement deterministic inference for various reasons, but it is possible.

[qeternity → gpugreg]

Most people are not even referring to CUDA batching nuances.

They think that sampling is an inherent part of Transformers.

Even on this site, it is regurgitated with confidence.